Post
96
Structured financial facts, each linked to the character in the filing it came from π°π
Today I am introducing two datasets and a model trained on them:
StockAlloy/filedfact-passages
A passage-complete dataset of phrases and the embedded financial facts.
StockAlloy/filedfact-100k
A fact-sampled version- one grounded financial fact per row, deep-linked to its source.
StockAlloy/filedfact-qwen3-8b
An 8B model fine-tuned to read a filing passage and return the facts as JSON.
Kroam1/filedfact-demo
Live demo - paste a passage, see the facts.
Today I am introducing two datasets and a model trained on them:
StockAlloy/filedfact-passages
A passage-complete dataset of phrases and the embedded financial facts.
StockAlloy/filedfact-100k
A fact-sampled version- one grounded financial fact per row, deep-linked to its source.
StockAlloy/filedfact-qwen3-8b
An 8B model fine-tuned to read a filing passage and return the facts as JSON.
Kroam1/filedfact-demo
Live demo - paste a passage, see the facts.